Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    page numbers

    oai_token-act-pair · gpt-3.5-turbo

    punctuation marks or commas in a text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ochond
    -0.72
    insula
    -0.61
     sclerosis
    -0.58
     plat
    -0.57
    etic
    -0.56
    '/
    -0.56
     behavi
    -0.55
    !--
    -0.55
     citiz
    -0.55
     exha
    -0.55
    POSITIVE LOGITS
    000
    1.19
    060
    0.88
    075
    0.84
    070
    0.84
    048
    0.84
    800
    0.81
    600
    0.79
     ISBN
    0.79
     preferably
    0.78
    040
    0.77
    Act Density 0.293%

    No Known Activations